Unterschiede

Hier werden die Unterschiede zwischen zwei Versionen angezeigt.

Link zu dieser Vergleichsansicht

Beide Seiten der vorigen RevisionVorhergehende Überarbeitung
Nächste Überarbeitung		Vorhergehende Überarbeitung
ai_ki [2025/08/13 13:35] – [TTS SST] muonitai_ki [2025/08/18 14:13] (aktuell) – [TTS] muonit
Zeile 15: Zeile 15:
   * https://meetcosmos.com/free-audio-transcription/   * https://meetcosmos.com/free-audio-transcription/
   * https://github.com/vllm-project/vllm   * https://github.com/vllm-project/vllm
 +  * https://kyutai.org/next/tts
 +  * https://github.com/KittenML/KittenTTS
  
  
Zeile 25: Zeile 27:
   * https://synexa.ai/explore/tencent/hunyuan3d-2 Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets   * https://synexa.ai/explore/tencent/hunyuan3d-2 Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets
   * https://huggingface.co/spaces/k2-fsa/text-to-speech   * https://huggingface.co/spaces/k2-fsa/text-to-speech
 +  * https://unmute.sh/
  
  
 ===== Lokal ===== ===== Lokal =====
 +  * https://github.com/google-ai-edge/gallery on cellphone AI models
 +  * https://github.com/ZeyueT/AudioX Anything to Audio
 +==== Chat ====
   * https://github.com/mezbaul-h/june Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit    * https://github.com/mezbaul-h/june Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit 
   * https://jan.ai/ Jan is an open source ChatGPT-alternative that runs 100% offline.   * https://jan.ai/ Jan is an open source ChatGPT-alternative that runs 100% offline.
 +
 +==== Bilder/Video ====
 +=== Hintergrund entfernen ===
   * https://bannerify.co/tools/remove-bg   * https://bannerify.co/tools/remove-bg
 +  * https://github.com/pinokiofactory/RMBG-2-Studio?tab=readme-ov-file
 +  * https://github.com/azizaydi23/video-bg-remover
 +
 +
 +=== Bildgenerierung ===
   * https://ltxv.video A groundbreaking 13B-parameter AI model by Lightricks, on a 4090/5090   * https://ltxv.video A groundbreaking 13B-parameter AI model by Lightricks, on a 4090/5090
-  * https://github.com/google-ai-edge/gallery on cellphone AI models+  * https://github.com/runew0lf/RuinedFooocus 
 +  * https://github.com/ant-research/MagicQuill 
 +  * https://github.com/deepbeepmeep/Hunyuan3D-2GP 3D Model from Image 
 + 
 +=== Clone Movement to Avatar/Videogenerierung === 
 +  * https://github.com/antgroup/echomimic_v2 Clone Movement to digital Avatar 
 +  * https://github.com/antgroup/echomimic_v3?tab=readme-ov-file 
 +  * https://github.com/deepbeepmeep/Wan2GP Open Source Video Generative Models Accessible to the GPU Poor 
 +  * https://github.com/IDEA-Research/DWPose Like OpenPose  
 + 
 +==== TTS ==== 
 +  * https://github.com/fishaudio/fish-speech SOTA Open Source TTS  - OpenAudio 
 +  * https://github.com/nari-labs/dia 
 +  * https://github.com/myshell-ai/OpenVoice Voice Cloning 
 +  * https://github.com/yl4579/StyleTTS2 
 +  * https://docs.hyprnote.com/owhisper/what-is-this OWhisper SST für Hyprnote 
 + 
 +==== STT ====
   * https://github.com/fastrepl/hyprnote Local-first AI Notepad for Private Meetings    * https://github.com/fastrepl/hyprnote Local-first AI Notepad for Private Meetings 
   * https://github.com/thewh1teagle/vibe  Transcribe on your own!    * https://github.com/thewh1teagle/vibe  Transcribe on your own! 
 +  * https://github.com/jhj0517/Whisper-WebUI Subtitle editing
 +  * https://github.com/RayFernando1337/MLX-Auto-Subtitled-Video-Generator/ Für M Macs
 +
 +